Is ColBERT superseded?

ColBERT (Retrieval-augmented generation): superseded — cited as a baseline and beaten by newer methods. 1 paper(s) critique it, 5 beat it on benchmarks — #34 of 1179 most-superseded. Sub-problem: cluster led by BM25. Newer alternatives in the same sub-problem include Beyond Topical Similarity, Experience-RAG Skill, LFRAG, Don't Retrieve, Navigate, MIGRASCOPE.

Retrieval-augmented generation

ColBERT

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT

Superseded baseline#34 of 1,179 most-superseded · first seen Apr 27, 2020

Superseded — cited as a baseline and beaten by newer methods

1 papers critique it · 5 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites ColBERT as a baseline.

While dense retrievers like Dense Passage Retrieval (DPR) and late-interaction models like ColBERT improve recall on single-hop queries, they often struggle with multi-hop reasoning, where the answer depends on composing information from multiple disjoint documents

— Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assembly

Beaten on benchmarks

Head-to-head results where a newer method reports beating ColBERT. Values are copied from the source paper's tables — verify against the cited paper.

GraphRAFT beats ColBERT
63.71 vs 11.75
Hit@1 · [STARK-PRIME]
GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databases
ft-DPR beats ColBERT
63.1 vs 17.6
R@1K · [512 tokens context]
CLERC: A Dataset for Legal Case Retrieval and Retrieval-Augmented Analysis Generation
CARROT beats ColBERT
0.349 vs 0.253
F1 · [HotpotQA 512 tokens]
CORAG: A Cost-Constrained Retrieval Optimization System for Retrieval-Augmented Generation
LeSeGR beats ColBERT
0.835 vs 0.769
Acc · [PapersWithCodeQA]
CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs
CAR beats ColBERT
15.733 vs 15.635
F1 · [ColBERT reranker]
CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.